AI Paper Atlas

Research map / Continual learning / Online and replay-based

Crafting Your Evolving Dreams: Concept-Incremental Versatile Customization

Jiahua Dong, Wenqi Liang, Hongliu Li, Yang Cong, Duzhen Zhang, hanbin zhao, Henghui Ding, Yulun Zhang, Salman Khan, Fahad Shahbaz Khan

TPAMI 2026 · Continual learning › Online and replay-based · approach: Dynamic expansion and isolation · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add LCT module (ablation)Base · Single-concept text-to-image (SDXL)FIA: 9.44 -> 8.36Improved
add LCT module (ablation)Base · Single-concept text-to-image (SDXL)IA: 64.89 -> 65.18Improved
add LCT module (ablation)Base · Single-concept text-to-image (SDXL)TA: 80.28 -> 80.05No clear effect
add FGA module (ablation)Base+LCT · Single-concept text-to-image (SDXL)IA: 65.18 -> 65.76Improved
add FGA module (also cuts parameters) (ablation)Base+LCT · Single-concept text-to-image (SDXL)#Params: 6.43M -> 4.72MImproved
add MKB module (ablation)Base+LCT+FGA · Single-concept text-to-image (SDXL)FIA: 8.06 -> 7.18Improved
add MKB module (fewer parameters) (ablation)Base+LCT+FGA · Single-concept text-to-image (SDXL)#Params: 4.72M -> 4.23MImproved
add RGA module (ablation)Base+LCT+FGA+MKB · Single-concept text-to-image (SDXL)IA: 66.25 -> 72.84Improved
add RGA module (ablation)Base+LCT+FGA+MKB · Single-concept text-to-image (SDXL)FIA: 7.18 -> 3.84Improved
add RGA module (ablation)Base+LCT+FGA+MKB · Single-concept text-to-3D (SDXL)FIA: 5.54 -> 2.89Improved
use CCDM instead of CIDM (conference version)CIDM · Single-concept text-to-image (SDXL)FIA: 8.35 -> 3.84Improved
use CCDM instead of CIDM with fewer parametersCIDM · Multi-concept text-to-image (SDXL)IA: 72.12 -> 77.25Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy